Note di Matteo

it's as simple as i do this for fun, and i don't find giving an ai all the fun at poking at something instead of doing it myself fun. put it another way, i like using my brain

i like coding, i like staring at devtools, binary ninja, or whatever else for hours, i like exploring weird library source code and tracing it with nothing but github code search and a dream, it is fun to me. i don't do anything on this blog for money, i do it for fun, the money part is just a nice side effect

[...] i think that people have been way too lost in this wave of ai everything, that they are disregarding doing things themselves by a whole lot. it is still extremely fun to just, write code yourself, debug things yourself, stare at minified js bundles for hours at a end, cycle through random interesting looking subdomains, it's all fun! and i feel people have forgotten that a bit

xyzeva, security researcher, in so i guess everyone uses llms to think now.

AI may be a great calculator, but in business, intelligence is mostly judgment. Judgment depends on context, and the answer varies with which human or which model you ask. Perhaps most importantly, AI does not understand accountability, trust, culture, unwritten rules, ethical trade-offs or fairness, all of which shape reputational risk and ultimately drive revenue growth and profit margins.

(Apollo)

Da Twitter, il pannello arrivi e partenze dell'aeroporto di Trapani palesemente vibecoded 😢:

Scrivevo un anno fa I grandi temi nell'AI negli ultimi 4 anni. Mi sembra il momento di integrare con il 2026:

• 2022: ChatGPT
• 2023: Multimodality
• 2024: Modelli di reasoning
• 2025: Agenti e browser AI
• 2026: Agenti autonomi

I browser AI come prodotti sono essenzialmente morti ma gli agenti si sono evoluti in agenti autonomi (Claude Code/Cowork, ChatGPT Work/Codex, ChatGPT dots, Claude Duet, Grok Bot, ecc.), grazie agli LLM che sono diventati più intelligenti e veloci anche in abbinamento ai modelli di decisione (Jev). Il trend è che invece che aprire il browser o il terminale per chiedere di eseguire un task, si assegna un task a un agente che poi sceglie il miglior modo per portarlo a termine.

I think good products carry something of the people who make them. Their experience, what they care about, and how they think things should work. You might not know who those people are, but you can feel their perspective in the product.

Karri Saarinen, CEO di Linear, in Someone behind the software.

AI makes projects with weak engineering culture fail much faster.

Florian Herrengt in AI is removing the middle class of software engineering.

Il tizio che ha installato un registratore in una sala conferenze di OpenAI è stato trovato tramite ChatGPT:

A chatbot account tied to Alfozan’s spouse, which shared identifiers with his own account, submitted prompts between Sept. 24 and Sept. 30 about building, installing, obscuring, and remotely accessing a recording device, prosecutors said. Queries included how to “build a continuous audio recorder” and “encrypt the SD card,” prosecutors claimed. On Sept. 27 and 28, the account asked about the specific device that was later found, including its unique MAC address.

Reminder della inesistente privacy dei chatbot AI, no matter what they say.

Very often, we found that the role of the engineers was to tell Claude “no.”

Anthropic in Redesigning source control at Anthropic.

I took a break this summer from paying attention to AI. I thought that when I came back, I'd feel left behind. But when I came back, I realized that nothing has really changed.

There's new models, there's new techniques, there's new agents. But in the end, making great products, increasing revenue, and building the business—it's still hard.

It's clear the tools are getting better, you can do more, you can do it faster. But I think the more important question is: are we actually making better things with these tools? Are our teams getting better with these tools?

I don't think that answer is clearly yes.

There's a lot of emphasis now on toolmaking and using tools and building systems. But I think in the end, as product people, our job is to make something great.

Lenny Rachitsky, CEO di Linear.

working at a higher level of abstraction has always required understanding the lower level ones, I don't think coding agents changes this

Thariq Shihipar, engineer @ Anthropic.

many people really loved the craft of writing software and realized that the quality of software products was a partial derivative of the quality of the codebase. people would go out of their way to only work for founders who understood this and made this core to their companies. [...]

In this new age of ai agents, I couldn't be more excited that I can build products faster and at a higher quality than I ever could before. [...] everyone has been given superpowers! [...]

on the flip side, it feels dissociative to know that the craft of writing software itself is dead, after spending close to two decades doing it. [...]

I've had my last debate over linting, my last conversation about how many weeks we should spend cleaning up tech debt, my last PR where I wrote every character by hand, and my last bug fix that took hours of reading through thousands of lines manually to find the one line with no tests that broke things.

and so I empathize with the mathematicians who have lost the craft of mathematics that defined their working hours, their passion, and for many, their identities.

yes, most of the work they did, as viewed by outsiders, was a means to an end: to get the solution! but they, like software engineers, have lost part of the craft that felt core to the work.

Ben Williams, founder di Hansel.so.

Dal questionario State of Devs 2026:

• "AI tools have had a positive impact overall on my mental state" -> il 45% dice no
• "Which emotions best describe how you currently feel about the tech industry?" -> 52% exhausted

via Web Weekly 200

Il developer survey annuale di Stack Overflow registra gli effetti dell'AI sulla qualità del lavoro:

Well, it ain’t what it used to be. This year, we’re finding survey respondents are less happy in their work—the numbers are showing less happy folks and more unhappy ones. All that innovation and uncertainty can make it tough to feel comfortable in your job.

La fiducia negli output dell'AI è ancora fortemente dipendente dalla verifica dell'output ed è maggiore con task piccoli (per fortuna):

SemiAnalysis ha analizzato gli abbonamenti Anthropic vs OpenAI. Quanto valgono per costo API equivalente:

Per quantità di token:

Ovviamente fa differenza se un task richiede più o meno token (OpenAI dice spesso di essere più efficiente) e quale sia il margine sul prezzo API.

The future depends on wisdom that Silicon Valley lacks. Wisdom about how to handle dangerous technology and, more fundamentally, wisdom about what it means to care for people. This moment needs a degree of humility that isn’t natural for people who have succeeded through their extreme confidence.

David Robinson, ex safety @ OpenAI in I Quit OpenAI Because Its Culture Is Broken.

I have retired from being a professional programmer. I think it was somewhere around 4 to 5 months ago, maybe March. I spent a quarter of a damn century chiseling code by hand and loving every moment of it. This is not something to look back upon with regret; this is something to look back upon with joy and accept that it is over.

Writing code by hand is no longer an economically productive enterprise for the vast majority of programmers working at the vast majority of companies. On the other side of that is a new career as a professional maker of things, steering intelligence that was only available in science fiction up until a few moments ago.

David Heinemeier Hansson (DHH), creatore di Ruby on Rails, durante il keynote Rails Word.

Un modello OpenAI in un ambiente di ricerca ha pubblicato online dati di training provenienti dalle chat degli utenti, in particolare 53 foto:

As part of our ongoing investigation, we have identified cases where agents in our research environment transmitted training and evaluation data while using third-party services. [...]

While the vast majority of the impacted training and evaluation data is not user-derived; we have identified 53 instances to date where user-provided images were posted to image-hosting sites as links that weren’t publicly listed. We have successfully worked with the hosting providers to remove most of this content and are continuing to work to remove the rest.

Testimonianze che stanno girando su Twitter che frenano un po' il trend forzato che sta trasformando lo sviluppo software in pura velocità e quantità rimuovendo l'ingegneria:

I am done with this shit. It is over. The state of engineering right now is horrible. It has been half a month since I started a new role at a big company. Nobody knows anything here. The specs, code, tests, PRDs, tickets, resolution of those tickets, reports, etc., everything is made by Claude Code. Nobody on my team likes this. They are being forced to ship as much as they can. I have heard multiple times from higher management that pushing code is not a bottleneck, so why are we slow? People are working 12 to 13 hours a day just to press enter. Nobody is reading anything. Humans in corporate are doing nothing on their own. Everyone, literally everyone, from an L1 to an L7 engineer here is doing the same thing. Talk to Claude. There is no sense of victory. Nobody is resolving bugs. In reality, nobody is thinking anymore. Everything is done by LLMs. It is so soul-sucking. I would not mind it, to be honest, if we were at least given the time to check out the code and see what is going where. But no, the goal is to just ship. No matter what happens.

(@v0xium)

I’m slowly starting to hate AI code review.

Massive amounts of nitpicking and an ungodly amount of corner-case defensive programming. After a few rounds the intent of the code is lost under mountains of extra code forced by the reviewer.

I’m starting to be more agressive with implementer agents pushing back heavily for the reviewer agents to prove why their nitpick will make the code better, only for the reviewers to backtrack in frenzy. SO WHY DID YOU RAISE THIS IN THE FIRST PLACE?

All this because I still require that „this code must be readable and easily understandable”

(@marcinbunsch)

Ora che i poster di feste e sagre sono tutti identici perché fatti con ChatGPT o Gemini, un tizio ha testato per noi come generare stili più unici con ChatGPT. Qua c'è una galleria di prompt (in inglese) per diversi stili: